Update app.py

app.py

@@ -162,18 +162,19 @@ app.prepare(ctx_id=0, det_size=(640, 640))
 
 
 # download checkpoints
-hf_hub_download(repo_id="briaai/ID_preservation_2.3_auraFaceEnc", filename="checkpoint_105000/controlnet/config.json", local_dir="./checkpoints2")
-hf_hub_download(repo_id="briaai/ID_preservation_2.3_auraFaceEnc", filename="checkpoint_105000/controlnet/diffusion_pytorch_model.safetensors", local_dir="./checkpoints2")
-hf_hub_download(repo_id="briaai/ID_preservation_2.3_auraFaceEnc", filename="checkpoint_105000/ip-adapter.bin", local_dir="./checkpoints2")
-hf_hub_download(repo_id="briaai/ID_preservation_2.3_auraFaceEnc", filename="image_encoder/pytorch_model.bin", local_dir="./checkpoints2")
-hf_hub_download(repo_id="briaai/ID_preservation_2.3_auraFaceEnc", filename="image_encoder/config.json", local_dir="./checkpoints2")
+print("Downloading checkpoints")
+hf_hub_download(repo_id="briaai/ID_preservation_2.3_auraFaceEnc", filename="checkpoint_105000/controlnet/config.json", local_dir="./checkpoints")
+hf_hub_download(repo_id="briaai/ID_preservation_2.3_auraFaceEnc", filename="checkpoint_105000/controlnet/diffusion_pytorch_model.safetensors", local_dir="./checkpoints")
+hf_hub_download(repo_id="briaai/ID_preservation_2.3_auraFaceEnc", filename="checkpoint_105000/ip-adapter.bin", local_dir="./checkpoints")
+hf_hub_download(repo_id="briaai/ID_preservation_2.3_auraFaceEnc", filename="image_encoder/pytorch_model.bin", local_dir="./checkpoints")
+hf_hub_download(repo_id="briaai/ID_preservation_2.3_auraFaceEnc", filename="image_encoder/config.json", local_dir="./checkpoints")
 
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
 # ckpts paths
-face_adapter = f"./checkpoints2/ip-adapter.bin"
-controlnet_path = f"./checkpoints2/controlnet"
+face_adapter = f"./checkpoints/ip-adapter.bin"
+controlnet_path = f"./checkpoints/controlnet"
 base_model_path = f'briaai/BRIA-2.3'
 resolution = 1024
 
@@ -186,7 +187,7 @@ controlnet = [controlnet_lnmks, controlnet_canny]
 
 
 image_encoder = CLIPVisionModelWithProjection.from_pretrained(
-        f"./checkpoints2/image_encoder",
+        f"./checkpoints/image_encoder",
         torch_dtype=torch.float16,
     )
 pipe = StableDiffusionXLInstantIDPipeline.from_pretrained(